© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 42296
    Prev
    Next
    INDEX
    Explanations

    Source code and odd text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     herald
    -0.29
    _HAL
    -0.26
    ç«ŀ
    -0.26
     tả
    -0.26
    ara
    -0.26
    hall
    -0.25
    亡
    -0.25
    妥
    -0.25
     quieter
    -0.24
    å±ħ
    -0.24
    POSITIVE LOGITS
    ä¸ĥåįģ
    0.33
    Specification
    0.29
     sixty
    0.28
    ä¸īåįģ
    0.26
    6
    0.26
     xx
    0.26
    edException
    0.26
    åħŃåįģ
    0.26
    çŃ¾ä¸ĭ
    0.25
     seventy
    0.25
    Activations Density 0.000%

    No Known Activations